mlsanityData to 14 Oct 2026

WITT: A Wireless Image Transmission Transformer for Semantic Communications

arXiv 2211.00937 ↗First posted 2 Nov 2022cs.CV cs.IT math.ITcited by 37

Not on the map. Why?

Abstract (arXiv)

In this paper, we aim to redesign the vision Transformer (ViT) as a new backbone to realize semantic image transmission, termed wireless image transmission transformer (WITT). Previous works build upon convolutional neural networks (CNNs), which are inefficient in capturing global dependencies, resulting in degraded end-to-end transmission performance especially for high-resolution images. To tackle this, the proposed WITT employs Swin Transformers as a more capable backbone to extract long-range information. Different from ViTs in image classification tasks, WITT is highly optimized for image transmission while considering the effect of the wireless channel. Specifically, we propose a spatial modulation module to scale the latent representations according to channel state information, which enhances the ability of a single model to deal with various channel conditions. As a result, extensive experiments verify that our WITT attains better performance for different image resolutions, distortion metrics, and channel conditions. The code is available at https://github.com/KeYang8/WITT.

Key facts. Cited by 37 papers in the map (data through 14 Oct 2026). Builds on 7 of its 23 references that are in the map. First posted on arXiv 2 Nov 2022.

Builds on

7 of 23 references.

References · 7

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  3. 2020Deep Learning Enabled Semantic Communication Systemscited by 292
  4. 2019DeepJSCC-f: Deep Joint Source-Channel Coding of Images with Feedbackcited by 96
  5. 2018Deep Learning for Joint Source-Channel Coding of Textcited by 69
  6. 2020Wireless Image Retrieval at the Edgecited by 59
  7. 2022Perceptual Learned Source-Channel Coding for High-Fidelity Image Semantic Transmissioncited by 12

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 5; 2024: 12; 2025: 12; 2026: 8.

37 papers.

Sort:

By area:

  1. 2023CDDM: Channel Denoising Diffusion Models for Wireless Semantic Communicationscited by 59
  2. 2023CDDM: Channel Denoising Diffusion Models for Wireless Communicationscited by 19
  3. 2024Visual Language Model based Cross-modal Semantic Communication Systemscited by 12
  4. 2024Diffusion-Aided Joint Source Channel Coding For High Realism Wireless Image Transmissioncited by 11
  5. 2024Robust Image Semantic Coding with Learnable CSI Fusion Masking over MIMO Fading Channelscited by 9
  6. 2024Semantic Successive Refinement: A Generative AI-aided Semantic Communication Frameworkcited by 9
  7. 2023Segment Anything Meets Semantic Communicationcited by 8
  8. 2024Importance-Aware Image Segmentation-based Semantic Communication for Autonomous Drivingcited by 7
  9. 2024DM-MIMO: Diffusion Models for Robust Semantic Communications over MIMO Channelscited by 6
  10. 2024Generative Semantic Communication for Joint Image Transmission and Segmentationcited by 6
  11. 2025DeepSeek-Inspired Exploration of RL-based LLMs and Synergy with Wireless Networks: A Surveycited by 6
  12. 2023An Efficient Federated Learning Framework for Training Semantic Communication Systemcited by 5
25 more
  1. 2025Multi-user Wireless Image Semantic Transmission over MIMO Multiple Access Channelscited by 4
  2. 2024Transformer-Aided Semantic Communicationscited by 3
  3. 2024Efficient Semantic Communication Through Transformer-Aided Compressioncited by 3
  4. 2025Semantic Edge-Cloud Communication for Real-Time Urban Traffic Surveillance with ViT and LLMs over Mobile Networkscited by 3
  5. 2023Semantic Multi-Resolution Communicationscited by 2
  6. 2024FSSC: Federated Learning of Transformer Neural Networks for Semantic Image Communicationcited by 2
  7. 2025From Large AI Models to Agentic AI: A Tutorial on Future Intelligent Communicationscited by 2
  8. 2024SC-CDM: Enhancing Quality of Image Semantic Communication with a Compact Diffusion Modelcited by 1
  9. 2025Modeling and Performance Analysis for Semantic Communications Based on Empirical Resultscited by 1
  10. 2025SecDiff: Diffusion-Aided Secure Deep Joint Source-Channel Coding Against Adversarial Attackscited by 1
  11. 2025Wireless Video Semantic Communication with Decoupled Diffusion Multi-frame Compensationcited by 1
  12. 2026Scenario-Adaptive MU-MIMO OFDM Semantic Communication With Asymmetric Neural Networkcited by 1
  13. 2026Progressive Semantic Communication for Efficient Edge-Cloud Vision-Language Modelscited by 1
  14. 2024Interplay of Semantic Communication and Knowledge Learningcited by 0
  15. 2025Learnable Residual-Based Latent Denoising in Semantic Communicationcited by 0
  16. 2025Semantic Communication in Dynamic Channel Scenarios: Collaborative Optimization of Dual-Pipeline Joint Source-Channel Coding and Personalized Federated Learningcited by 0
  17. 2025TOAST: Task-Oriented Adaptive Semantic Transmission over Dynamic Wireless Environmentscited by 0
  18. 2025Way to Build Native AI-driven 6G Air Interface: Principles, Roadmap, and Outlookcited by 0
  19. 2025Synesthesia of Machines (SoM)-Based Task-Driven MIMO System for Image Transmissioncited by 0
  20. 2026On Privacy-Preserving Image Transmission in Low-Altitude Networks: A Swin Transformer-Based Framework with Federated Learningcited by 0
  21. 2026Quantum Machine Learning-based 6G edge Network: Enabling Adaptive Communication and Model Aggregationcited by 0
  22. 2026Semantic-Aware Generative Image Transmission for Resource-Constrained Visual IoT Systemscited by 0
  23. 2026ComVLA: Communication-Aware Split Inference for VLA Models in 6G-Connected Roboticscited by 0
  24. 2026Foundation Models for Generalizable Semantic and Goal-Oriented Communicationcited by 0
  25. 2026Beyond Token Accuracy: Prioritizing What Matters for Visual Reconstructioncited by 0